Jiahong 的个人博客

凡事预则立,不预则废


  • Home

  • Tags

  • Archives

  • Navigation

  • Search

NLPTag

NLP——Megatron-LM原始论文解读-第一篇

NLP——DeepSeek-GRM

NLP——LLM-as-a-judge

NLP——LLM对齐微调-DPO

NLP——LLM对齐微调-LLDS

NLP——Interplay-of-Pre-Mid-Post-Training-on-LRM

NLP——LLM对齐微调-GRPO

NLP——LLM对齐微调-Pass@k-Training

NLP——Agentic-AI相关技术简介

NLP——LoRA和QLoRA

1…131415…21
Joe Zhou

Joe Zhou

Stay Hungry. Stay Foolish.

652 posts
53 tags
GitHub E-Mail
© 2026 Joe Zhou
Powered by Hexo
|
Theme — NexT.Gemini v5.1.4